Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consequences or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doesnt
    -0.65
     didnt
    -0.61
     dont
    -0.59
    DragonMagazine
    -0.59
     whats
    -0.53
     alot
    -0.52
     secondly
    -0.52
     thous
    -0.51
     tyr
    -0.51
    yss
    -0.50
    POSITIVE LOGITS
    *.
    1.17
    .*
    1.11
    .[
    1.10
    .''.
    1.09
    .</
    1.05
    .''
    1.01
    .).
    0.99
    .
    0.98
    .ãĢį
    0.98
    .�
    0.94
    Act Density 2.329%

    No Known Activations